© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20640
    Prev
    Next
    INDEX
    Explanations

    this context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŁİå¸ĤçļĦ
    -0.09
    åīįæīĢ
    -0.08
    CUS
    -0.08
    (bs
    -0.08
    ophilia
    -0.08
     footprint
    -0.08
    _WS
    -0.08
    GPL
    -0.08
    ç³»
    -0.08
    å·®çĤ¹
    -0.08
    POSITIVE LOGITS
    çİ°éĺ¶æ®µ
    0.09
    iction
    0.09
    èĢĮè¨Ģ
    0.09
    æĥ¯
    0.09
    ystack
    0.09
    éĶĢ
    0.09
    versible
    0.09
    è¿Ĥ
    0.09
     context
    0.09
    æĿ¥è¯´
    0.09
    Activations Density 0.199%

    No Known Activations